Revisions of python-scikit-learn
buildservice-autocommit
accepted
request 1172097
from
Dirk Mueller (dirkmueller)
(revision 66)
baserev update by copy to link target
Dirk Mueller (dirkmueller)
accepted
request 1172001
from
Benjamin Greiner (bnavigator)
(revision 65)
- Unlock numpy 2 (but don't force it for build)
buildservice-autocommit
accepted
request 1169326
from
Dirk Mueller (dirkmueller)
(revision 64)
baserev update by copy to link target
Dirk Mueller (dirkmueller)
committed
(revision 63)
- update to 1.4.2: * This release only includes support for numpy 2.
buildservice-autocommit
accepted
request 1149083
from
Markéta Machová (mcalabkova)
(revision 62)
baserev update by copy to link target
Markéta Machová (mcalabkova)
accepted
request 1148118
from
Benjamin Greiner (bnavigator)
(revision 61)
- Update to 1.4.1.post1 ## Metadata Routing * Fix routing issue with ColumnTransformer when used inside another meta-estimator. #28188 by Adrin Jalali. * No error is raised when no metadata is passed to a metaestimator that includes a sub-estimator which doesn’t support metadata routing. #28256 by Adrin Jalali. * Fix multioutput.MultiOutputRegressor and multioutput.MultiOutputClassifier to work with estimators that don’t consume any metadata when metadata routing is enabled. #28240 by Adrin Jalali. ## DataFrame Support * Enhancement Fix Pandas and Polars dataframe are validated directly without ducktyping checks. #28195 by Thomas Fan. ## Changes impacting many modules * Efficiency Fix Partial revert of #28191 to avoid a performance regression for estimators relying on euclidean pairwise computation with sparse matrices. The impacted estimators are: - sklearn.metrics.pairwise_distances_argmin - sklearn.metrics.pairwise_distances_argmin_min - sklearn.cluster.AffinityPropagation - sklearn.cluster.Birch - sklearn.cluster.SpectralClustering - sklearn.neighbors.KNeighborsClassifier - sklearn.neighbors.KNeighborsRegressor - sklearn.neighbors.RadiusNeighborsClassifier - sklearn.neighbors.RadiusNeighborsRegressor - sklearn.neighbors.LocalOutlierFactor - sklearn.neighbors.NearestNeighbors - sklearn.manifold.Isomap - sklearn.manifold.TSNE - sklearn.manifold.trustworthiness - #28235 by Julien Jerphanion. * Fixes a bug for all scikit-learn transformers when using set_output with transform set to pandas or polars. The bug could lead to wrong naming of the columns of the returned dataframe. #28262 by Guillaume Lemaitre. * When users try to use a method in StackingClassifier, StackingClassifier, StackingClassifier, SelectFromModel, RFE, SelfTrainingClassifier, OneVsOneClassifier, OutputCodeClassifier or OneVsRestClassifier that their sub-estimators don’t implement, the AttributeError now reraises in the traceback. #28167 by Stefanie Senger. - Release 1.4.0 * HistGradientBoosting Natively Supports Categorical DTypes in DataFrames * Polars output in set_output * Missing value support for Random Forest * Add support for monotonic constraints in tree-based models * Enriched estimator displays * Metadata Routing Support * Improved memory and runtime efficiency for PCA on sparse data * Highlights and detailed changelog: * https://scikit-learn.org/stable/auto_examples/release_highlights/plot_release_highlights_1_4_0.html * https://scikit-learn.org/stable/whats_new/v1.4.html#release-notes-1-4 - Enable python312 test flavor, avoid testing it with the other flavors - Prepare for python39 flavor drop
buildservice-autocommit
accepted
request 1124107
from
Dirk Mueller (dirkmueller)
(revision 60)
baserev update by copy to link target
Dirk Mueller (dirkmueller)
committed
(revision 59)
- update to 1.3.2: * All dataset fetchers now accept `data_home` as any object that implements the :class:`os.PathLike` interface, for instance, :class:`pathlib.Path`. * Fixes a bug in :class:`decomposition.KernelPCA` by forcing the output of the internal :class:`preprocessing.KernelCenterer` to be a default array. When the arpack solver is used, it expects an array with a `dtype` attribute. * Fixes a bug for metrics using `zero_division=np.nan` (e.g. :func:`~metrics.precision_score`) within a paralell loop (e.g. :func:`~model_selection.cross_val_score`) where the singleton for `np.nan` will be different in the sub-processes. * Do not leak data via non-initialized memory in decision tree pickle files and make the generation of those files deterministic. * Ridge models with `solver='sparse_cg'` may have slightly different results with scipy>=1.12, because of an underlying change in the scipy solver * The `set_output` API correctly works with list input. * :class:`calibration.CalibratedClassifierCV` can now handle models that produce large prediction scores. - Skip another recalcitrant test on 32 bit. * We are in the process of introducing a new way to route metadata such as sample_weight throughout the codebase, which would affect how meta-estimators such as pipeline.Pipeline and * Originally hosted in the scikit-learn-contrib repository, * A new category encoding strategy preprocessing.TargetEncoder encodes the categories based on a shrunk estimate of the average * The classes tree.DecisionTreeClassifier and tree.DecisionTreeRegressor * model_selection.ValidationCurveDisplay is now available to plot
buildservice-autocommit
accepted
request 1103058
from
Steve Kowalik (StevenK)
(revision 58)
baserev update by copy to link target
Steve Kowalik (StevenK)
committed
(revision 57)
- Skip another recalcitrant test on 32 bit.
buildservice-autocommit
accepted
request 1101760
from
Markéta Machová (mcalabkova)
(revision 56)
baserev update by copy to link target
Markéta Machová (mcalabkova)
accepted
request 1101759
from
Markéta Machová (mcalabkova)
(revision 55)
- Python flavors shifted again, drop test-py38, add test-py311 Sadly, it still fails in the numpy staging
buildservice-autocommit
accepted
request 1100745
from
Dirk Mueller (dirkmueller)
(revision 54)
baserev update by copy to link target
Dirk Mueller (dirkmueller)
accepted
request 1100585
from
Markéta Machová (mcalabkova)
(revision 53)
- Update to 1.3.0 * We are in the process of introducing a new way to route metadata such as sample_weight throughout the codebase, which would affect how meta-estimators such as pipeline.Pipeline and model_selection.GridSearchCV route metadata. * Originally hosted in the scikit-learn-contrib repository, cluster.HDBSCAN has been adopted into scikit-learn. * A new category encoding strategy preprocessing.TargetEncoder encodes the categories based on a shrunk estimate of the average target values for observations belonging to that category. * The classes tree.DecisionTreeClassifier and tree.DecisionTreeRegressor now support missing values. * model_selection.ValidationCurveDisplay is now available to plot results from model_selection.validation_curve * The class ensemble.HistGradientBoostingRegressor supports the Gamma deviance loss function via loss="gamma". * Similarly to preprocessing.OneHotEncoder, the class preprocessing.OrdinalEncoder now supports aggregating infrequent categories into a single output for each feature. * More changes, see https://scikit-learn.org/stable/whats_new/v1.3.html
buildservice-autocommit
accepted
request 1092217
from
Dirk Mueller (dirkmueller)
(revision 52)
baserev update by copy to link target
Dirk Mueller (dirkmueller)
accepted
request 1092146
from
Eric Schirra (ecsos)
(revision 51)
- Add %{?sle15_python_module_pythons}
buildservice-autocommit
accepted
request 1064381
from
Matej Cepl (mcepl)
(revision 50)
baserev update by copy to link target
Matej Cepl (mcepl)
accepted
request 1063913
from
Arun Persaud (apersaud)
(revision 49)
update to latest version
buildservice-autocommit
accepted
request 1058774
from
Matej Cepl (mcepl)
(revision 48)
baserev update by copy to link target
Matej Cepl (mcepl)
accepted
request 1058551
from
Benjamin Greiner (bnavigator)
(revision 47)
- Update to version 1.2.0 * Pandas output with set_output API * Interaction constraints in Histogram-based Gradient Boosting Trees * New and enhanced displays * Faster parser in fetch_openml * Experimental Array API support in LinearDiscriminantAnalysis * Improved efficiency of many estimators - Drop sklearn-pr24283-gradient-segfault.patch - PEP517 build
Displaying revisions 1 - 20 of 66